{
  "abstract": "We study federated online reinforcement learning with linear function approximation. While recent multi-agent reinforcement learning algorithms achieve strong regret guarantees, they typically require sharing raw trajectories. This reliance incurs a communication cost that scales linearly with the number of episodes and violates the privacy constraints of federated settings. To address these limitations, we propose Fed-LSVI, the first provably efficient federated algorithm for online reinforcement learning with linear function approximation in episodic Markov decision processes. By integrating a determinant-based event-triggered synchronization with a stepwise backward update mechanism, Fed-LSVI enables agents to collaboratively learn an optimal policy by exchanging only compressed sufficient statistics. We prove that Fed-LSVI achieves a regret bound of $\\widetilde{\\mathcal O}(\\sqrt{Md^3H^4T})$, where $d$ is the feature dimension, $H$ is the horizon length, $M$ is the number of agents, and $T$ is the number of episodes per agent, matching the best-known regret for multi-agent online reinforcement learning with linear function approximation. Moreover, by following the stringent communication and privacy constraints of the federated setting, Fed-LSVI reduces the communication cost to only logarithmic dependence on $T$, representing a significant improvement over prior methods.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.00193",
  "author_total": 3,
  "authors": [
    {
      "name": "Zihang Liang"
    },
    {
      "name": "Haochen Zhang"
    },
    {
      "name": "Lingzhou Xue"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/7eddyrx5psk7x.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.00193",
  "fulltext_url": null,
  "id": "7eddyrx5psk7x",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.00193",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1702|Reinforcement Learning in Robotics"
    ]
  ],
  "openalex": "W7206173067",
  "pdf_url": "https://arxiv.org/pdf/2609.00193",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/7eddyrx5psk7x.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:18:10Z",
      "native_id": "2609.00193",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.00193"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "Provably Efficient Federated Reinforcement Learning with Linear Function Approximation and Logarithmic Communication Cost",
  "title_text": "Provably Efficient Federated Reinforcement Learning with Linear Function Approximation and Logarithmic Communication Cost",
  "type": "preprint",
  "updated_at": "2026-10-30T12:18:10Z",
  "url": "https://research.draconitic.com/paper/7eddyrx5psk7x",
  "venue": "arXiv",
  "versions": []
}